English
Related papers

Related papers: Test-Time Alignment via Hypothesis Reweighting

200 papers

We address the issue of tuning hyperparameters (HPs) for imitation learning algorithms in the context of continuous-control, when the underlying reward function of the demonstrating expert cannot be observed at any time. The vast literature…

The performance of large language models (LLMs) across diverse downstream applications is fundamentally governed by the quality and composition of their pretraining corpora. Existing domain reweighting algorithms primarily optimize data…

Machine Learning · Computer Science 2025-05-28 Simin Fan , Maria Ios Glarou , Martin Jaggi

We propose Re-FORC, an adaptive reward prediction method that, given a context, enables prediction of the expected future rewards as a function of the number of future thinking tokens. Re-FORC trains a lightweight adapter on reasoning…

Artificial Intelligence · Computer Science 2025-11-05 Renos Zabounidis , Aditya Golatkar , Michael Kleinman , Alessandro Achille , Wei Xia , Stefano Soatto

We propose to personalize a human pose estimator given a set of test images of a person without using any manual annotations. While there is a significant advancement in human pose estimation, it is still very challenging for a model to…

Computer Vision and Pattern Recognition · Computer Science 2021-11-09 Yizhuo Li , Miao Hao , Zonglin Di , Nitesh B. Gundavarapu , Xiaolong Wang

To improve human-preference alignment training, current research has developed numerous preference datasets consisting of preference pairs labeled as "preferred" or "dispreferred". These preference pairs are typically used to encode human…

Computation and Language · Computer Science 2024-10-08 Chenglong Wang , Yang Gan , Yifu Huo , Yongyu Mu , Qiaozhi He , Murun Yang , Tong Xiao , Chunliang Zhang , Tongran Liu , Jingbo Zhu

Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different amounts of reasoning effort depending on how they value…

Artificial Intelligence · Computer Science 2025-11-13 Michael Kleinman , Matthew Trager , Alessandro Achille , Wei Xia , Stefano Soatto

Recommender systems have achieved great success in modeling user's preferences on items and predicting the next item the user would consume. Recently, there have been many efforts to utilize time information of users' interactions with…

Information Retrieval · Computer Science 2021-04-30 Junsu Cho , Dongmin Hyun , SeongKu Kang , Hwanjo Yu

Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning from human feedback (RLHF). However, current reward models…

Computation and Language · Computer Science 2024-10-24 Rui Yang , Ruomeng Ding , Yong Lin , Huan Zhang , Tong Zhang

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises others (e.g., harmlessness) due to the inherent conflicts…

Computation and Language · Computer Science 2025-04-16 Zhihao Xu , Yongqi Tong , Xin Zhang , Jun Zhou , Xiting Wang

Human Pose (HP) estimation is actively researched because of its wide range of applications. However, even estimators pre-trained on large datasets may not perform satisfactorily due to a domain gap between the training and test data. To…

Computer Vision and Pattern Recognition · Computer Science 2023-11-10 Hiromu Taketsugu , Norimichi Ukita

The use of past experiences to accelerate temporal difference (TD) learning of value functions, or experience replay, is a key component in deep reinforcement learning. Prioritization or reweighting of important experiences has shown to…

Artificial Intelligence · Computer Science 2020-06-24 Samarth Sinha , Jiaming Song , Animesh Garg , Stefano Ermon

In this article, we investigate the alignment of Large Language Models according to human preferences. We discuss the features of training a Preference Model, which simulates human preferences, and the methods and details we found essential…

Machine Learning · Computer Science 2024-10-03 Alexey Kutalev , Sergei Markoff

Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large language models (LLMs) with human preferences. Generative reward models (GRMs) provide greater…

Machine Learning · Computer Science 2026-04-21 Ai Jian , Jingqing Ruan , Xing Ma , Xiaoyun Zhang , Dailin Li , Weipeng Zhang , Ke Zeng , Xunliang Cai

Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. The so-called algorithm, Reinforcement Learning with Human Feedback (RLHF) demonstrates impressive…

Computation and Language · Computer Science 2023-02-13 Tianjun Zhang , Fangchen Liu , Justin Wong , Pieter Abbeel , Joseph E. Gonzalez

Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individual users. This relies on personalized reward models that capture user-specific preferences…

Computation and Language · Computer Science 2026-04-21 Hongru Cai , Yongqi Li , Tiezheng Yu , Fengbin Zhu , Wenjie Wang , Fuli Feng , Wenjie Li

We propose a novel reinforcement learning framework for post training large language models that does not rely on human in the loop feedback. Instead, our approach uses cross attention signals within the model itself to derive a self…

Artificial Intelligence · Computer Science 2025-04-18 Andrew Kiruluta , Andreas Lemos , Priscilla Burity

We investigate a narrow but common failure mode of GRPO-style reinforcement learning in the context of sparse verifiable rewards: early updates contain more responses with negative advantages than those with positive advantages, while…

Machine Learning · Computer Science 2026-05-29 Mohamed Sana , Nicola Piovesan , Antonio De Domenico , Fadhel Ayed , Haozhe Zhang

Most of the existing approaches for person re-identification consider a static setting where the number of cameras in the network is fixed. An interesting direction, which has received little attention, is to explore the dynamic nature of a…

Computer Vision and Pattern Recognition · Computer Science 2020-08-07 Sk Miraj Ahmed , Aske R Lejbølle , Rameswar Panda , Amit K. Roy-Chowdhury

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Artificial Intelligence · Computer Science 2025-10-20 Keertana Chidambaram , Karthik Vinary Seetharaman , Vasilis Syrgkanis

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Machine Learning · Computer Science 2025-10-21 Keertana Chidambaram , Karthik Vinay Seetharaman , Vasilis Syrgkanis